© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 9-RES-JB
    11. 20760
    Prev
    Next
    INDEX
    Explanations

    adjectives describing various qualities or characteristics

    oai_token-act-pair · gpt-3.5-turbo

    the word "rather" and its context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    elsen
    -0.87
    iliate
    -0.83
    ULTS
    -0.78
    illary
    -0.76
    Reviewed
    -0.74
    ulkan
    -0.73
    uay
    -0.73
    adium
    -0.73
    ividual
    -0.71
    rats
    -0.70
    POSITIVE LOGITS
     pathetic
    1.01
     than
    0.97
     amusing
    0.97
     pricey
    0.93
     pointless
    0.92
     tame
    0.91
     ironic
    0.91
     inconvenient
    0.90
     boring
    0.90
     cryptic
    0.89
    Activations Density 0.025%

    No Known Activations